%0 Generic %1 Nakayama_wikipedialink %A Nakayama, Kotaro %A Hara, Takahiro %A Nishio, Shojiro %D 2008 %K wikisempaths %T Wikipedia Link Structure and Text Mining for Semantic Relation Extraction Towards a Huge Scale Global Web Ontology %U http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.1537 %X Abstract. Wikipedia, a collaborative Wiki-based encyclopedia, has become a huge phenomenon among Internet users. It covers huge number of concepts of various fields such as Arts, Geography, History, Science, Sports and Games. Since it is becoming a database storing all human knowledge, Wikipedia mining is a promising approach that bridges the Semantic Web and the Social Web (a. k. a. Web 2.0). In fact, in the previous researches on Wikipedia mining, it is strongly proved that Wikipedia has a remarkable capability as a corpus for knowledge extraction, especially for relatedness measurement among concepts. However, semantic relatedness is just a numerical strength of a relation but does not have an explicit relation type. To extract inferable semantic relations with explicit relation types, we need to analyze not only the link structure but also texts in Wikipedia. In this paper, we propose a consistent approach of semantic relation extraction from Wikipedia. The method consists of three sub-processes highly optimized for Wikipedia mining; 1) fast preprocessing, 2) POS (Part Of Speech) tag tree analysis, and 3) mainstay extraction. Furthermore, our detailed evaluation proved that link structure mining improves both the accuracy and the scalability of semantic relations extraction. 1

@misc{Nakayama_wikipedialink, abstract = {Abstract. Wikipedia, a collaborative Wiki-based encyclopedia, has become a huge phenomenon among Internet users. It covers huge number of concepts of various fields such as Arts, Geography, History, Science, Sports and Games. Since it is becoming a database storing all human knowledge, Wikipedia mining is a promising approach that bridges the Semantic Web and the Social Web (a. k. a. Web 2.0). In fact, in the previous researches on Wikipedia mining, it is strongly proved that Wikipedia has a remarkable capability as a corpus for knowledge extraction, especially for relatedness measurement among concepts. However, semantic relatedness is just a numerical strength of a relation but does not have an explicit relation type. To extract inferable semantic relations with explicit relation types, we need to analyze not only the link structure but also texts in Wikipedia. In this paper, we propose a consistent approach of semantic relation extraction from Wikipedia. The method consists of three sub-processes highly optimized for Wikipedia mining; 1) fast preprocessing, 2) POS (Part Of Speech) tag tree analysis, and 3) mainstay extraction. Furthermore, our detailed evaluation proved that link structure mining improves both the accuracy and the scalability of semantic relations extraction. 1}, added-at = {2012-08-25T15:03:25.000+0200}, author = {Nakayama, Kotaro and Hara, Takahiro and Nishio, Shojiro}, biburl = {https://www.bibsonomy.org/bibtex/2aaaf24bea751e6a41650e8be1d1df425/psinger}, description = {CiteSeerX — Wikipedia Link Structure and Text Mining for Semantic Relation Extraction Towards a Huge Scale Global Web Ontology}, interhash = {360729c79f17997cdd2d63a58616e487}, intrahash = {aaaf24bea751e6a41650e8be1d1df425}, keywords = {wikisempaths}, timestamp = {2012-09-26T16:03:47.000+0200}, title = {Wikipedia Link Structure and Text Mining for Semantic Relation Extraction Towards a Huge Scale Global Web Ontology}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.1537}, year = 2008 }